中文
相关论文

相关论文: Context-Guided Diffusion for Out-of-Distribution M…

200 篇论文

Diffusion models have emerged as powerful generative models for graph generation, yet their use for conditional graph generation remains a fundamental challenge. In particular, guiding diffusion models on graphs under arbitrary reward…

机器学习 · 计算机科学 2025-05-27 Victor M. Tenorio , Nicolas Zilberstein , Santiago Segarra , Antonio G. Marques

Guidance in conditional diffusion generation is of great importance for sample quality and controllability. However, existing guidance schemes are to be desired. On one hand, mainstream methods such as classifier guidance and…

机器学习 · 计算机科学 2023-10-18 Jiajun Ma , Tianyang Hu , Wenjia Wang , Jiacheng Sun

Despite the recent advancements, conditional image generation still faces challenges of cost, generalizability, and the need for task-specific training. In this paper, we propose Manifold Preserving Guided Diffusion (MPGD), a training-free…

Diffusion models have demonstrated empirical successes in various applications and can be adapted to task-specific needs via guidance. This paper studies a form of gradient guidance for adapting a pre-trained diffusion model towards…

机器学习 · 统计学 2024-10-17 Yingqing Guo , Hui Yuan , Yukang Yang , Minshuo Chen , Mengdi Wang

Diffusion models, a powerful and universal generative AI technology, have achieved tremendous success in computer vision, audio, reinforcement learning, and computational biology. In these applications, diffusion models provide flexible…

机器学习 · 计算机科学 2024-04-12 Minshuo Chen , Song Mei , Jianqing Fan , Mengdi Wang

Conditional diffusion models have exhibited superior performance in high-fidelity text-guided visual generation and editing. Nevertheless, prevailing text-guided visual diffusion models primarily focus on incorporating text-visual…

计算机视觉与模式识别 · 计算机科学 2024-06-05 Ling Yang , Zhilong Zhang , Zhaochen Yu , Jingwei Liu , Minkai Xu , Stefano Ermon , Bin Cui

Generative models on discrete state-spaces have a wide range of potential applications, particularly in the domain of natural sciences. In continuous state-spaces, controllable and flexible generation of samples with desired properties has…

机器学习 · 计算机科学 2025-03-27 Hunter Nisonoff , Junhao Xiong , Stephan Allenspach , Jennifer Listgarten

Diffusion models have shown promise in forecasting future data from multivariate time series. However, few existing methods account for recurring structures, or patterns, that appear within the data. We present Pattern-Guided Diffusion…

机器学习 · 计算机科学 2025-12-17 Vivian Lin , Kuk Jin Jang , Wenwen Si , Insup Lee

Recent advances in diffusion-based generative models have shown incredible promise for zero shot image-to-image translation and editing. Most of these approaches work by combining or replacing network-specific features used in the…

计算机视觉与模式识别 · 计算机科学 2025-10-06 Zeqi Gu , Ethan Yang , Abe Davis

Recent advances in diffusion models have shown remarkable potential in the conditional generation of novel molecules. These models can be guided in two ways: (i) explicitly, through additional features representing the condition, or (ii)…

机器学习 · 计算机科学 2025-03-12 Yuchen Shen , Chenhao Zhang , Sijie Fu , Chenghui Zhou , Newell Washburn , Barnabás Póczos

Discrete diffusion models are a class of generative models that construct sequences by progressively denoising samples from a categorical noise distribution. Beyond their rapidly growing ability to generate coherent natural language, these…

计算与语言 · 计算机科学 2025-12-11 Michael Cardei , Jacob K Christopher , Thomas Hartvigsen , Bhavya Kailkhura , Ferdinando Fioretto

Can we train a 3D molecule generator using data from dense regions to generate samples in sparse regions? This challenge can be framed as an out-of-distribution (OOD) generation problem. While prior research on OOD generation predominantly…

机器学习 · 计算机科学 2026-03-03 Haokai Hong , Wanyu Lin , Ming Yang , Kay Chen Tan

Controllable molecular graph generation is essential for material and drug discovery, where generated molecules must satisfy diverse property constraints. While recent advances in graph diffusion models have improved generation quality,…

机器学习 · 计算机科学 2025-09-30 Anjie Qiao , Zhen Wang , Chuan Chen , DeFu Lian , Enhong Chen

Recent advancements have explored text-to-image diffusion models for synthesizing out-of-distribution (OOD) samples, substantially enhancing the performance of OOD detection. However, existing approaches typically rely on perturbing…

计算机视觉与模式识别 · 计算机科学 2025-10-28 Xin Gao , Jiyao Liu , Guanghao Li , Yueming Lyu , Jianxiong Gao , Weichen Yu , Ningsheng Xu , Liang Wang , Caifeng Shan , Ziwei Liu , Chenyang Si

Recent advancements in diffusion models have revolutionized generative modeling. However, the impressive and vivid outputs they produce often come at the cost of significant model scaling and increased computational demands. Consequently,…

机器学习 · 计算机科学 2025-04-03 Jincheng Zhong , Xiangcheng Zhang , Jianmin Wang , Mingsheng Long

Effectively designing molecular geometries is essential to advancing pharmaceutical innovations, a domain, which has experienced great attention through the success of generative models and, in particular, diffusion models. However, current…

生物大分子 · 定量生物学 2025-01-07 Sirine Ayadi , Leon Hetzel , Johanna Sommer , Fabian Theis , Stephan Günnemann

Modifications to test-time sampling have emerged as an important extension to diffusion algorithms, with the goal of biasing the generative process to achieve a given objective without having to retrain the entire diffusion model. However,…

机器学习 · 计算机科学 2026-04-21 Hao Luan , Yi Xian Goh , See-Kiong Ng , Chun Kai Ling

Diffusion models for continuous data gained widespread adoption owing to their high quality generation and control mechanisms. However, controllable diffusion on discrete data faces challenges given that continuous guidance methods do not…

We propose Context Diffusion, a diffusion-based framework that enables image generation models to learn from visual examples presented in context. Recent work tackles such in-context learning for image generation, where a query image is…

计算机视觉与模式识别 · 计算机科学 2025-07-24 Ivona Najdenkoska , Animesh Sinha , Abhimanyu Dubey , Dhruv Mahajan , Vignesh Ramanathan , Filip Radenovic

Text-conditioned molecular generation aims to translate natural-language descriptions into chemical structures, enabling scientists to specify functional groups, scaffolds, and physicochemical constraints without handcrafted rules.…

机器学习 · 计算机科学 2025-11-18 Lingxiao Li , Haobo Zhang , Bin Chen , Jiayu Zhou
‹ 上一页 1 2 3 10 下一页 ›